Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    proper nouns and formal identifiers in a legal or academic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.80
     CreateTagHelper
    -0.78
    RegressionTest
    -0.66
    '},
    -0.61
    "},
    -0.59
    HomeAsUpEnabled
    -0.58
    IndentedString
    -0.58
    createConnection
    -0.57
    tilhe
    -0.56
    cahontas
    -0.55
    POSITIVE LOGITS
     thine
    0.58
    Manbalar
    0.56
     Thine
    0.54
    matchCondition
    0.53
    Lähteet
    0.53
     kwiat
    0.53
    named
    0.52
     Personalis
    0.51
    zczegól
    0.51
     named
    0.51
    Act Density 1.249%

    No Known Activations